Yi-Jen Wang

Learn More
This paper proposes Runge-Kutta neural networks (RKNNs) for identification of unknown dynamical systems described by ordinary differential equations (i.e., ordinary differential equation or ODE systems) with high accuracy. These networks are constructed according to the Runge-Kutta approximation method. The main attraction of the RKNNs is that they(More)
Enterovirus type 71 (EV71) 2A protease exhibited strong transcriptional activity in yeast cells. The transcriptional activity of 2A protease was independent of its protease activity. EV71 2A protease retained its transcriptional activity after truncation of 40 amino acids at the N-terminus but lost this activity after truncation of 60 amino acids at the(More)
Special protection system (SPS) can ensure power grids to operate in a satisfactory state following a contingency or major disturbances. By installing phasor measurement units (PMUs), the stability indices can be computed and applied to the decision system of a response-based SPS for recognizing the pattern of system instability. In this paper, the integral(More)
The United Nations proclaimed that the year 1981 was the International Year of Disabled Persons. Countries worldwide vigorously promote a barrier-free environment to achieve the goal of equal opportunities and full participation. Therefore, providing disabled students with a barrier-free campus environment is an issue that demands substantial attention from(More)
In recent years, Orthogonal Frequency Division Multiplexing (OFDM) technology has been widely used in many wireless communication systems, including LTE and WiMAX. Bandwidth is always precious over wireless channel, so it is important to have an effective bandwidth arrangement. On a multi-user system, each user needs to share entire bandwidth with others.(More)
In our observations, some Japanese companies tend to ask their suppliers to become involved in their procurement of materials and/or joint product development projects, with undefined requests as proposals. We tried to comprehend this curious phenomenon by developing a unique analytical framework. We use the " Hiding hand effect " concept to explain how the(More)
This article proposes a new second-order learning algorithm for training the multilayer perceptron (MLP) networks. The proposed algorithm is a revised Newton's method. A forward–backward propagation scheme is first proposed for network computation of the Hessian matrix, H, of the output error function of the MLP. A block Hessian matrix, H b , is then(More)
  • 1